INDEX

Explanations

references to daemon processes and system components in technical contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

equ

-0.16

met

-0.15

ke

-0.15

tw

-0.15

acin

-0.15

unh

-0.14

à¹ĥà¸ļ

-0.14

gu

-0.14

env

-0.14

bac

-0.14

POSITIVE LOGITS

-valu

0.17

otate

0.17

$MESS

0.16

è®¤è¯Ĩ

0.16

ULD

0.16

-Javadoc

0.16

Äħd

0.15

SCO

0.15

ujet

0.15

ombat

0.15

Activations Density 0.014%

references to daemon processes and system components in technical contexts

No Comments

No Known Activations